© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34266
    Prev
    Next
    INDEX
    Explanations

    dates and years

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric tokens (e.g. numbers or number‐like strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     without
    -1.30
     natten
    -1.12
     at
    -1.12
     vinter
    -1.10
     with
    -1.01
     cannot
    -0.97
    preneurs
    -0.96
     назвать
    -0.93
     tider
    -0.92
    俳優
    -0.92
    POSITIVE LOGITS
     trám
    1.16
     umożliwia
    1.03
     ersche
    0.99
     nhung
    0.98
     giang
    0.96
     reagiert
    0.96
    alleg
    0.94
     européennes
    0.94
     zawsze
    0.92
     erreich
    0.92
    Activations Density 0.013%

    No Known Activations